転置インデックス圧縮1 • Basically, to process a query we need to traverse the inverted lists of the query terms • Lists are very long and are stored on disks • Challenge: traverse lists as quickly as possible • Tricks: compression, caching, parallelism, early termination (“pruning”) Recap: Search Engine Query Processing • Parallel query processing: divide docs between many machines, broadcast results to all • Cachin
